Denken

Denkmodelle werden darauf trainiert, den „Denkprozess“ zu generieren, den das Modell im Rahmen seiner Antwort durchläuft. Daher können Thinking Models in ihren Antworten besser argumentieren als vergleichbare Basismodelle.

Der Denkprozess ist standardmäßig aktiviert. Wenn Sie Vertex AI Studio verwenden, können Sie den gesamten Denkprozess zusammen mit der generierten Antwort des Modells ansehen.

Unterstützte Modelle

Die Funktion „Denken“ wird in den folgenden Modellen unterstützt:

Denkmodell verwenden

So verwenden Sie die Funktion „Thinking“ mit einem unterstützten Modell:

Console

  1. Öffnen Sie Vertex AI Studio > Prompt erstellen.
  2. Klicken Sie im Bereich Modell auf Modell wechseln und wählen Sie im Menü eines der unterstützten Modelle aus.
    • (Nur Gemini 2.5 Flash) Das Denkbudget ist beim Laden des Modells standardmäßig auf Automatisch eingestellt.
  3. (Optional) Geben Sie dem Modell im Feld Systemanweisungen detaillierte Anweisungen dazu, wie es seine Antworten formatieren soll.
  4. Geben Sie einen Prompt in das Feld Prompt eingeben ein.
  5. Klicken Sie auf  Ausführen.

Gemini gibt eine Antwort zurück, nachdem sie generiert wurde. Je nach Komplexität der Antwort kann die Generierung mehrere Sekunden dauern.

(Nur Gemini 2.5 Flash) Wenn Sie die Denkprozesse deaktivieren möchten, setzen Sie Budget für Denkprozesse auf Aus.

Python

Installieren

pip install --upgrade google-genai

Weitere Informationen finden Sie in der SDK-Referenzdokumentation.

Umgebungsvariablen für die Verwendung des Gen AI SDK mit Vertex AI festlegen:

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

from google import genai

client = genai.Client()
response = client.models.generate_content(
    model="gemini-2.5-pro",
    contents="solve x^2 + 4x + 4 = 0",
)
print(response.text)
# Example Response:
#     Okay, let's solve the quadratic equation x² + 4x + 4 = 0.
#
#     We can solve this equation by factoring, using the quadratic formula, or by recognizing it as a perfect square trinomial.
#
#     **Method 1: Factoring**
#
#     1.  We need two numbers that multiply to the constant term (4) and add up to the coefficient of the x term (4).
#     2.  The numbers 2 and 2 satisfy these conditions: 2 * 2 = 4 and 2 + 2 = 4.
#     3.  So, we can factor the quadratic as:
#         (x + 2)(x + 2) = 0
#         or
#         (x + 2)² = 0
#     4.  For the product to be zero, the factor must be zero:
#         x + 2 = 0
#     5.  Solve for x:
#         x = -2
#
#     **Method 2: Quadratic Formula**
#
#     The quadratic formula for an equation ax² + bx + c = 0 is:
#     x = [-b ± sqrt(b² - 4ac)] / (2a)
#
#     1.  In our equation x² + 4x + 4 = 0, we have a=1, b=4, and c=4.
#     2.  Substitute these values into the formula:
#         x = [-4 ± sqrt(4² - 4 * 1 * 4)] / (2 * 1)
#         x = [-4 ± sqrt(16 - 16)] / 2
#         x = [-4 ± sqrt(0)] / 2
#         x = [-4 ± 0] / 2
#         x = -4 / 2
#         x = -2
#
#     **Method 3: Perfect Square Trinomial**
#
#     1.  Notice that the expression x² + 4x + 4 fits the pattern of a perfect square trinomial: a² + 2ab + b², where a=x and b=2.
#     2.  We can rewrite the equation as:
#         (x + 2)² = 0
#     3.  Take the square root of both sides:
#         x + 2 = 0
#     4.  Solve for x:
#         x = -2
#
#     All methods lead to the same solution.
#
#     **Answer:**
#     The solution to the equation x² + 4x + 4 = 0 is x = -2. This is a repeated root (or a root with multiplicity 2).

Zusammenfassungen von Gedanken ansehen

Zusammenfassungen der Überlegungen sind die abgekürzte Ausgabe des Denkprozesses, den das Modell beim Generieren seiner Antwort durchlaufen hat. Zusammenfassungen der Gedankengänge sind sowohl in Gemini 2.5 Flash als auch in Gemini 2.5 Pro verfügbar. So rufen Sie Zusammenfassungen von Gedanken auf:

Console

Zusammenfassungen von Gedanken sind in Vertex AI Studio standardmäßig aktiviert. Sie können den zusammengefassten Denkprozess des Modells sehen, indem Sie den Bereich Gedanken maximieren.

Python

Installieren

pip install --upgrade google-genai

Weitere Informationen finden Sie in der SDK-Referenzdokumentation.

Umgebungsvariablen für die Verwendung des Gen AI SDK mit Vertex AI festlegen:

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

from google import genai
from google.genai.types import GenerateContentConfig, ThinkingConfig

client = genai.Client()
response = client.models.generate_content(
    model="gemini-2.5-pro",
    contents="solve x^2 + 4x + 4 = 0",
    config=GenerateContentConfig(
        thinking_config=ThinkingConfig(include_thoughts=True)
    ),
)

print(response.text)
# Example Response:
#     Okay, let's solve the quadratic equation x² + 4x + 4 = 0.
#     ...
#     **Answer:**
#     The solution to the equation x² + 4x + 4 = 0 is x = -2. This is a repeated root (or a root with multiplicity 2).

for part in response.candidates[0].content.parts:
    if part and part.thought:  # show thoughts
        print(part.text)
# Example Response:
#     **My Thought Process for Solving the Quadratic Equation**
#
#     Alright, let's break down this quadratic, x² + 4x + 4 = 0. First things first:
#     it's a quadratic; the x² term gives it away, and we know the general form is
#     ax² + bx + c = 0.
#
#     So, let's identify the coefficients: a = 1, b = 4, and c = 4. Now, what's the
#     most efficient path to the solution? My gut tells me to try factoring; it's
#     often the fastest route if it works. If that fails, I'll default to the quadratic
#     formula, which is foolproof. Completing the square? It's good for deriving the
#     formula or when factoring is difficult, but not usually my first choice for
#     direct solving, but it can't hurt to keep it as an option.
#
#     Factoring, then. I need to find two numbers that multiply to 'c' (4) and add
#     up to 'b' (4). Let's see... 1 and 4 don't work (add up to 5). 2 and 2? Bingo!
#     They multiply to 4 and add up to 4. This means I can rewrite the equation as
#     (x + 2)(x + 2) = 0, or more concisely, (x + 2)² = 0. Solving for x is now
#     trivial: x + 2 = 0, thus x = -2.
#
#     Okay, just to be absolutely certain, I'll run the quadratic formula just to
#     double-check. x = [-b ± √(b² - 4ac)] / 2a. Plugging in the values, x = [-4 ±
#     √(4² - 4 * 1 * 4)] / (2 * 1). That simplifies to x = [-4 ± √0] / 2. So, x =
#     -2 again – a repeated root. Nice.
#
#     Now, let's check via completing the square. Starting from the same equation,
#     (x² + 4x) = -4. Take half of the b-value (4/2 = 2), square it (2² = 4), and
#     add it to both sides, so x² + 4x + 4 = -4 + 4. Which simplifies into (x + 2)²
#     = 0. The square root on both sides gives us x + 2 = 0, therefore x = -2, as
#      expected.
#
#     Always, *always* confirm! Let's substitute x = -2 back into the original
#     equation: (-2)² + 4(-2) + 4 = 0. That's 4 - 8 + 4 = 0. It checks out.
#
#     Conclusion: the solution is x = -2. Confirmed.

Budget für Denkprozesse steuern

Sie können festlegen, wie viel das Modell bei seinen Antworten überlegen soll. Diese Obergrenze wird als Denkbudget bezeichnet und gilt für den gesamten Denkprozess des Modells. Standardmäßig steuert das Modell automatisch, wie viel es sich ausdenkt,bis zu einem Maximum von 8.192 Tokens.

Sie können das obere Limit für die Anzahl der Tokens manuell festlegen, wenn Sie mehr oder weniger Tokens als das Standardbudget für Denkprozesse benötigen. Sie können für weniger komplexe Aufgaben ein niedrigeres Tokenlimit und für komplexere Aufgaben ein höheres Limit festlegen.

In der folgenden Tabelle sehen Sie die Mindest- und Höchstbeträge, die Sie für das Tokenbudget für jedes unterstützte Modell festlegen können:

Modell Mindestanzahl an Tokens Maximale Tokenanzahl
Gemini 2.5 Flash 1 24.576
Gemini 2.5 Pro 128 32.768
Gemini 2.5 Flash-Lite 512 24.576

Wenn Sie das Denkbudget auf 0 festlegen, wird die Denkfunktion bei Verwendung von Gemini 2.5 Flash und Gemini 2.5 Flash-Lite deaktiviert. Bei Gemini 2.5 Pro kann die Denkfunktion nicht deaktiviert werden.

Wenn das Modell das Thinking-Budget bei der Verwendung der API steuern soll, legen Sie das Thinking-Budget auf -1 fest.

Console

  1. Öffnen Sie Vertex AI Studio > Prompt erstellen.
  2. Klicken Sie im Bereich Modell auf Modell wechseln und wählen Sie im Menü eines der unterstützten Modelle aus.
  3. Wählen Sie im Drop-down-Menü Budget für Denkprozesse die Option Manuell aus und passen Sie dann das Limit für das Budget für Denkprozesse mit dem Schieberegler an.

Python

Installieren

pip install --upgrade google-genai

Weitere Informationen finden Sie in der SDK-Referenzdokumentation.

Umgebungsvariablen für die Verwendung des Gen AI SDK mit Vertex AI festlegen:

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

from google import genai
from google.genai.types import GenerateContentConfig, ThinkingConfig

client = genai.Client()

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="solve x^2 + 4x + 4 = 0",
    config=GenerateContentConfig(
        thinking_config=ThinkingConfig(
            thinking_budget=1024,  # Use `0` to turn off thinking
        )
    ),
)

print(response.text)
# Example response:
#     To solve the equation $x^2 + 4x + 4 = 0$, you can use several methods:
#     **Method 1: Factoring**
#     1.  Look for two numbers that multiply to the constant term (4) and add up to the coefficient of the $x$ term (4).
#     2.  The numbers are 2 and 2 ($2 \times 2 = 4$ and $2 + 2 = 4$).
#     ...
#     ...
#     All three methods yield the same solution. This quadratic equation has exactly one distinct solution (a repeated root).
#     The solution is **x = -2**.

# Token count for `Thinking`
print(response.usage_metadata.thoughts_token_count)
# Example response:
#     886

# Total token count
print(response.usage_metadata.total_token_count)
# Example response:
#     1525

Techniken für Prompts

Effektive Prompts sind entscheidend, um die Vorteile der Gemini-Denkmodelle zu maximieren. In diesem Abschnitt werden einige Prompting-Methoden für Denkmodelle beschrieben.

Beginnen Sie mit allgemeinen Anweisungen, die das gewünschte Ergebnis beschreiben. Beginnen Sie mit einem einfachen Prompt und beobachten Sie, wie das Modell reagiert.

Describe the most unusual or striking architectural feature you've ever seen in a building or structure.
  
<...>
The most unusual architectural feature that has truly stayed with me is the "floating roof" of the
  Heydar Aliyev Center in Baku, Azerbaijan, designed by Zaha Hadid Architects.

Visually, it's breathtaking. Imagine a vast, undulating landscape of pure white, seemingly draped
over the building. It's not just a roof in the traditional sense; it's an extension of the ground,
flowing seamlessly upwards and over the building's various spaces before curving back down to meet
the earth again. There are no sharp angles, no rigid lines. Instead, everything is fluid, organic,
and continuous. It resembles a giant, pristine white wave frozen in motion, or perhaps a sand dune
sculpted by an unseen wind.
<...>
  

Detaillierte Anleitung

Wenn der erste Versuch nicht das gewünschte Ergebnis liefert, können Sie Ihren Prompt verfeinern, indem Sie explizitere Schritt-für-Schritt-Anleitungen geben, um Gemini durch den Problemlösungsprozess zu führen. So können Sie das anfängliche Verständnis des Modells für die Aufgabe mit expliziten Vorschlägen und Anleitungen steuern.

Now imagine that architectural feature is not just for looks, but has a specific function or
purpose related to the building's environment or the people who use it. Explain what that
function could be and how it enhances the building's overall design and usability.
  
<...>
Let's imagine that the "floating roof" of the Heydar Aliyev Center is not purely aesthetic but
serves a crucial environmental and user-centric function: it's designed as a sophisticated climate
moderator and natural ventilation system for the Baku environment.

Here's how this function would work and enhance the building:

Function: Passive Climate Control and Natural Ventilation System

Shading and Solar Heat Mitigation: The undulating curves of the white GFRC roof are strategically
shaped and oriented to provide optimal shading throughout the day, year-round. Baku experiences
intense sun, especially during the summer. The overhanging curves, acting like giant brise-soleils,
would block direct sunlight from hitting the building's glass facade, significantly reducing solar
heat gain. The varying heights and depths of the curves would create dynamic shade patterns, ensuring
that different parts of the building are shaded at different times of the day, optimizing comfort
and reducing the need for excessive air conditioning. The white color of the GFRC further enhances
this by reflecting a large portion of the solar radiation.
<...>
  

Multishot-Prompting mit Denkschritten

Multishot-Prompts in Verbindung mit Thinking können das Verständnis von Gemini weiter verbessern und die Genauigkeit der Antworten erhöhen. Geben Sie in Ihrem Prompt mehrere Beispiele für Eingabe/Ausgabe-Paare an, die das gewünschte Verhalten und Ausgabeformat demonstrieren.

Example 1:
User: What is the tallest mountain in the world?
Assistant: Mount Everest

Example 2:
User: What is the largest ocean?
Assistant: Pacific Ocean

User: What is the longest river in the world?
Assistant:
  
Amazon River
  

Ausgabe und Verhalten definieren

Wenn Sie eine Anwendung entwickeln, in der Nutzer direkt mit dem Modell interagieren, sollten Sie angeben, wie die Ausgabe und die Antworten von Gemini klingen und formatiert werden sollen.

Systemanweisungen

Systemanweisungen sind eine Reihe von Anweisungen, die vom Modell verarbeitet werden, bevor es Prompts verarbeitet. Sie werden bei jedem Prompt an das Modell abgerufen und geben dem Modell vor, wie es sich verhalten und reagieren soll. Sie können beispielsweise die Rolle oder Identität, Kontextinformationen und Formatierungsanweisungen einfügen.

System Instruction: You are a helpful and concise coding tutor. Always provide code examples and explain them briefly.

User Prompt: Explain what is a closure in Javascript and give an example.
  
    function outerFunction(outerVar) {
      function innerFunction(innerVar) {
        console.log(outerVar); // Accessing outerVar from outerFunction's scope
        console.log(innerVar);
      }
      return innerFunction;
    }

    const closureExample = outerFunction('I am from outer');
    closureExample('I am from inner');

Explanation:

A closure is created when a function (innerFunction in this example) is defined inside another function
(outerFunction) and the inner function remembers and has access to the variables from the outer
function's scope, even after the outer function has finished executing.

In the example:

outerFunction is called with 'I am from outer' and returns innerFunction.

closureExample now holds a reference to innerFunction.

When closureExample('I am from inner') is called, innerFunction executes.

Even though outerFunction has already finished, innerFunction can still access and use outerVar
(which is 'I am from outer') because of the closure.

In essence, the innerFunction "closes over" the variables of its outer function's scope, creating
a closure.
  

Überprüfung und Reflexion

Geben Sie bestimmte Bestätigungsschritte entweder in den Systemanweisungen oder direkt in Ihren Prompts an. Sie können Gemini beispielsweise auffordern, die Quellen zu überprüfen, die Argumentation zu prüfen, potenzielle Fehler zu identifizieren und die endgültige Antwort zu überprüfen.

    Verify the following statement and provide your sources: The capital of Brazil is Rio de Janeiro.
  
The statement "The capital of Brazil is Rio de Janeiro" is incorrect.

The current capital of Brazil is Brasília.

Rio de Janeiro was the capital of Brazil for a significant period, from 1763 to 1960. However, the
capital was moved to Brasília in 1960 as part of a plan to develop the country's interior and create
a more centrally located capital.

Verification and Sources:

You can easily verify this information from numerous reliable sources:

Encyclopedias:

Britannica: Searching for "Brazil" on Britannica will clearly state Brasília as the capital.

https://www.britannica.com/place/Brazil (Look for the "Capital" information in the introductory summary or "Geography" section)

Wikipedia: The Wikipedia article for "Brazil" also states Brasília as the capital.

https://en.wikipedia.org/wiki/Brazil (Look in the infobox or introductory section)

Government and Official Sources:

CIA World Factbook: This is a highly reliable source for country information. Searching for "Brazil"
will list Brasília as the capital.

https://www.cia.gov/the-world-factbook/countries/brazil/ (Look under "Government" > "Capital")

Official Website of the Brazilian Government (if accessible and in English): While navigating official
government websites can sometimes be complex, they would definitively list Brasília as the capital.

Geographic Resources:

National Geographic: Their website and publications will confirm Brasília as the capital of Brazil.

Atlases and Geography Textbooks: Any modern atlas or geography textbook will list Brasília as the capital.

Why the confusion?

The confusion might arise because:

Rio de Janeiro is a very famous Brazilian city: It's a major tourist destination, known for its
beaches, Carnival, and iconic landmarks like Christ the Redeemer. Its past status as capital adds
to its historical significance and public recognition.

Historical context: Rio de Janeiro was the capital for a long time. People who learned about Brazil
in the past might remember it as the capital.

In conclusion, the statement is false. The capital of Brazil is Brasília, not Rio de Janeiro. Rio
de Janeiro was the former capital but is no longer the current capital.

You can confidently use the sources listed above to verify this information.
  

Debugging und Steuerung

In Vertex AI Studio haben Entwickler Zugriff auf die Überlegungen des Modells in der Benutzeroberfläche. Das ist hilfreich, wenn Sie als Entwickler Ihren Prompt beim Debuggen überprüfen:

Denkprozess analysieren

Sehen Sie sich den Denkprozess von Gemini genau an, um Bereiche zu identifizieren, in denen es möglicherweise zu Fehlern gekommen ist. Diese Analyse kann wertvolle Hinweise zur Optimierung Ihrer Prompts liefern, damit Sie in Ihrer Anwendung konsistent die erwartete Antwort erhalten.

Beispielszenario: Wenn aus dem Denkprozess von Gemini hervorgeht, dass ein Schritt in einer komplexen Anweisung falsch verstanden wurde, können Sie den Prompt verfeinern, um diesen Schritt zu verdeutlichen.

Step 1: Summarize the following article about quantum physics.
Step 2: Translate the summary into Spanish.
Step 3: Extract the key entities from the Spanish summary.

Article: ... [Article Text] ...
The user wants me to process an article about Google's new quantum chip called Willow in three steps:
Step 1: Summarize the article.
Step 2: Translate the summary into Spanish.
Step 3: Extract the key entities from the Spanish summary.

Let's break down each step.

Step 1: Summarize the article.
I need to read the article and identify the main points. The article is about Google's new quantum
chip, Willow, and its achievements. The key achievements are:

Exponential error reduction as qubits scale up.

Outperforming supercomputers in a benchmark computation (RCS).

Willow is a step towards commercially relevant quantum computing.

It's the first system below threshold for quantum error correction.

It achieved a benchmark computation in under 5 minutes that would take a supercomputer 10 septillion years.

It was fabricated in a new facility.

It has state-of-the-art performance and high quality qubits.

Google is looking towards real-world applications with Willow.

Quantum computing will benefit AI.

I will synthesize these points into a concise summary.

Step 2: Translate the summary into Spanish.
Once I have the summary in English, I will translate it into Spanish. I need to ensure the translation
is accurate and natural-sounding in Spanish.

Step 3: Extract the key entities from the Spanish summary.
After translating the summary, I will identify and extract the key entities. Key entities are typically
nouns or noun phrases that represent important objects, concepts, or actors. In this context, they
will likely include:

Names of chips (Willow, Sycamore)

Companies/Organizations (Google Quantum AI, Google Research)

Technologies (quantum chip, quantum computer, qubits, quantum error correction, superconducting
quantum system, classical computers, supercomputers, AI)

Benchmarks (random circuit sampling, RCS)

People (Julian Kelly, Peter Shor, David Deutsch, Sergio Boixo, Hartmut Neven, John Preskill)

Concepts (exponential error reduction, below threshold, beyond breakeven, state-of-the-art performance,
commercially relevant applications, quantum mechanics, multiverse, T1 times, system benchmarks,
algorithmic benchmarks)

I will need to carefully review the Spanish summary to identify these entities and list them out.

Provide corrective feedback

If you observe errors or inconsistencies in Gemini's reasoning, provide corrective feedback in your prompt and the system instructions to anticipate where the model's response may deviate from your desired outcome.

You are an expert in botany. When asked to identify a plant, focus on leaf shape, flower structure, and stem characteristics.

Identify this plant based on these characteristics: ... [Plant Characteristics Description] ...

Previous incorrect response focused on habitat only. Please disregard habitat and focus on morphology.
Previous incorrect response focused on habitat only. Please disregard habitat and focus on morphology.
Tabebuia vellosoi

Lange Ausgaben und ausführliche Überlegungen optimal nutzen

Durch „Thinking“ werden „Gedanken“ als Teil der Token-Ausgabe generiert, die die detaillierte Argumentation von Gemini zeigen. So nutzen Sie diese Ausgaben optimal:

Begründung ansehen

Achten Sie genau auf den Denkprozess von Gemini (verfügbar in der Vertex AI Studio-Benutzeroberfläche), wie die Aufgabe aufgeschlüsselt wurde und welche Entscheidungen für die Ausgabe getroffen wurden. So können Sie nachvollziehen, wie das Modell zu seiner Schlussfolgerung gelangt ist.

Orientierung beim Erstellen von Begründungen bieten

Wenn Sie eine besonders lange Ausgabe wünschen, sollten Sie in Ihrem Prompt mehr Anleitung geben, um den Aufwand für die Aufgabe im Prompt zu begrenzen. So können Sie mehr Token für Ihre Antwort reservieren.

*Beispiel: Für einen detaillierten Bericht können Sie in Ihrem Prompt Abschnitte und Unterabschnitte angeben, um Gemini bei der Strukturierung der Ausgabe zu unterstützen.

Generate a detailed report on the impact of climate change on coastal ecosystems.

Report Structure:

Introduction

Rising Sea Levels
2.1. Impact on Mangroves
2.2. Impact on Coral Reefs

Ocean Acidification
3.1. Impact on Shellfish
3.2. Impact on Plankton

Extreme Weather Events
4.1. Increased Storm Intensity
4.2. Coastal Erosion

Conclusion

Provide detailed analysis within each section.
<...>
Climate Change Impact on Coastal Ecosystems: A Detailed Report

1.  Introduction

Coastal ecosystems, the dynamic interface between land and sea, are among the most productive and
biodiverse environments on Earth. They provide crucial ecosystem services, including coastal protection,
fisheries, carbon sequestration, and support for a vast array of species. However, these vital
ecosystems are increasingly threatened by the multifaceted impacts of climate change. Driven by
anthropogenic greenhouse gas emissions, climate change is manifesting in several interconnected ways
that are profoundly altering the physical and chemical conditions of coastal environments. This report
will delve into the key impacts of climate change on coastal ecosystems, focusing on rising sea levels,
ocean acidification, and extreme weather events, and their specific consequences for critical habitats
like mangroves and coral reefs, and key organisms like shellfish and plankton. Understanding these
impacts is crucial for developing effective conservation and management strategies to mitigate the
damage and enhance the resilience of these invaluable ecosystems.

2.  Rising Sea Levels

Rising sea levels are a direct and significant consequence of global warming, driven by thermal
expansion of seawater and the melting of land ice (glaciers and ice sheets). This phenomenon poses a
direct threat to low-lying coastal ecosystems by inundating habitats, altering salinity regimes, and
increasing erosion rates. The rate of sea level rise is accelerating, and projections for the 21st
century indicate a continued upward trend, with potentially devastating consequences for coastal
environments.

2.1. Impact on Mangroves

Mangrove forests are unique coastal ecosystems found in tropical and subtropical intertidal zones.
They provide numerous benefits, including coastal protection against storms, nursery grounds for
fish and invertebrates, and significant carbon sequestration...
<...>

Nächste Schritte

Colab-Notebook oder Vertex AI-Konsole